{"id":"https://openalex.org/W7166834154","doi":"https://doi.org/10.18653/v1/2026.findings-acl.653","title":"Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models","display_name":"Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166834154","doi":"https://doi.org/10.18653/v1/2026.findings-acl.653"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.653","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.653","pdf_url":"https://aclanthology.org/2026.findings-acl.653.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.653.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135101424","display_name":"Rei Minamoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rei Minamoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139776695","display_name":"Yusuke Oda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Oda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139794531","display_name":"Daisuke Kawahara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daisuke Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82391744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13341","last_page":"13354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3149000108242035,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3149000108242035,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.09889999777078629,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.05730000138282776,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.33820000290870667},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33149999380111694},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.29829999804496765},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.296999990940094},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.23579999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728000044822693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5838000178337097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519000291824341},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.23579999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2305999994277954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.653","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.653","pdf_url":"https://aclanthology.org/2026.findings-acl.653.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.653","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.653","pdf_url":"https://aclanthology.org/2026.findings-acl.653.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6528543829917908,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166834154.pdf","grobid_xml":"https://content.openalex.org/works/W7166834154.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sensitive":[0],"personal":[1,42,57,63],"information":[2,17,30,43,64,102],"can":[3,99],"appear":[4],"in":[5,32,47,92,114],"large-scale":[6],"pre-training":[7],"corpora":[8],"for":[9],"large":[10],"language":[11],"models":[12,87],"(LLMs).Detecting":[13],"and":[14,27,36,83],"filtering":[15],"such":[16],"is":[18,107],"therefore":[19],"essential":[20],"to":[21,34,88,104,110],"ensure":[22],"compliance":[23],"with":[24],"privacy":[25],"regulations":[26],"prevent":[28],"unintended":[29],"leakage.However,":[31],"contrast":[33],"English":[35],"other":[37],"languages,":[38],"research":[39],"into":[40],"sensitive":[41,56],"has":[44],"been":[45],"limited":[46],"the":[48,70,108,119],"Japanese":[49,115],"language.In":[50],"this":[51],"study,":[52],"we":[53],"focus":[54],"on":[55,69],"data":[58],"defined":[59],"as":[60],"special":[61],"care-required":[62],"(SCPI)":[65],"under":[66],"Japan's":[67],"Act":[68],"Protection":[71],"of":[72,121],"Personal":[73],"Information":[74],"(APPI).We":[75],"construct":[76],"an":[77],"SCPI":[78,91,97,112],"dataset":[79],"using":[80],"LLM-based":[81],"annotation":[82],"train":[84],"machine":[85],"learning":[86],"rapidly":[89],"detect":[90],"text.As":[93],"a":[94],"result,":[95],"our":[96],"classifier":[98],"effectively":[100],"identify":[101],"related":[103],"SCPI.This":[105],"study":[106],"first":[109],"explore":[111],"detection":[113],"text":[116],"corpora,":[117],"highlighting":[118],"challenges":[120],"accurate":[122],"detection.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}